import tensorflow as tf
import streamlit as st
# import cv2
from PIL import Image
from streamlit_image_select import image_select
# import os

def load_and_prep_image(filename, img_shape=224, scale=True):
  """
  Reads in an image from filename, turns it into a tensor and reshapes into
  (224, 224, 3).

  Parameters
  ----------
  filename (str): string filename of target image
  img_shape (int): size to resize target image to, default 224
  scale (bool): whether to scale pixel values to range(0, 1), default True
  """
  # # Read in the image
  # img = tf.io.read_file(filename)
  # # Decode it into a tensor
  # img = tf.io.decode_image(img)
  img = tf.convert_to_tensor(filename)
  # Resize the image
  img = tf.image.resize(img, [img_shape, img_shape])
  if scale:
    # Rescale the image (get all values between 0 and 1)
    return img/255.
  else:
    return img

class_names = ['apple_pie', 'baby_back_ribs', 'baklava', 'beef_carpaccio', 'beef_tartare', 'beet_salad', 'beignets',
    'bibimbap', 'bread_pudding', 'breakfast_burrito', 'bruschetta', 'caesar_salad', 'cannoli', 'caprese_salad', 'carrot_cake', 
    'ceviche', 'cheese_plate', 'cheesecake', 'chicken_curry', 'chicken_quesadilla', 'chicken_wings', 'chocolate_cake',
    'chocolate_mousse', 'churros', 'clam_chowder', 'club_sandwich', 'crab_cakes', 'creme_brulee', 'croque_madame', 
    'cup_cakes', 'deviled_eggs', 'donuts', 'dumplings', 'edamame', 'eggs_benedict', 'escargots', 'falafel', 'filet_mignon', 
    'fish_and_chips', 'foie_gras', 'french_fries', 'french_onion_soup', 'french_toast', 'fried_calamari', 'fried_rice', 
    'frozen_yogurt', 'garlic_bread', 'gnocchi', 'greek_salad', 'grilled_cheese_sandwich', 'grilled_salmon', 'guacamole', 
    'gyoza', 'hamburger', 'hot_and_sour_soup', 'hot_dog', 'huevos_rancheros', 'hummus', 'ice_cream', 'lasagna', 'lobster_bisque', 
    'lobster_roll_sandwich', 'macaroni_and_cheese', 'macarons', 'miso_soup', 'mussels', 'nachos', 'omelette', 'onion_rings', 
    'oysters', 'pad_thai', 'paella', 'pancakes', 'panna_cotta', 'peking_duck', 'pho', 'pizza', 'pork_chop', 'poutine', 'prime_rib', 
    'pulled_pork_sandwich', 'ramen', 'ravioli', 'red_velvet_cake', 'risotto', 'samosa', 'sashimi', 'scallops', 'seaweed_salad', 
    'shrimp_and_grits', 'spaghetti_bolognese', 'spaghetti_carbonara', 'spring_rolls', 'steak', 'strawberry_shortcake', 'sushi', 
    'tacos', 'takoyaki', 'tiramisu', 'tuna_tartare', 'waffles']

#load model
@st.cache(allow_output_mutation = True)
def cache_model(model_name):
    model = tf.keras.models.load_model(model_name)
    return (model)
model = cache_model("101_food_class_100_percent_saved_big_model")
# model = tf.keras.models.load_model("101_food_class_100_percent_saved_big_model")

st.write("""
         # Food Classification App
         """
         )

st.write("""#### ***Upload food image and this app will classify the uploaded image from one of the mentioned categories.***""")

st.write("""
        **Some major food categories**
        ```
        pizza, cup_cakes, donuts, samosa, ice_cream, french_fries, waffles etc.
        ```
        for full categories list please visit the [link](https://github.com/gourav300/food_app)
        """)

### load file
uploaded_file = st.file_uploader("Upload an image file for above mentioned Food Categories or select a food image", type=["jpg", "png", "jpeg"])


test_img = image_select(
    label="Select a sample food image",
    images=[
        "test_images/Cardamom-Saffron-Cupcakes-1.jpg",
        "test_images/doughnut_1.jpg",
        "test_images/frenchfries.jpg",
        "test_images/Punjabi-Samosa-2.jpg",
        "test_images/dumpling.jpg",
        "test_images/pizza_1.jpg",
        "test_images/waffle.jpg",
        "test_images/pancake.jpg"
    ],
    captions=["Cupcake", "Doughnut", "French fries", "Samosa", "Dumpling", "Pizza", "Waffle", "Pancake"],
)

# st.set_option('deprecation.showfileUploaderEncoding', False)


if uploaded_file is not None:

    image = Image.open(uploaded_file)
    st.image(image,width = 500)#, use_column_width=True)
else:
    image = Image.open(test_img)
    st.image(image, width = 500)#,use_column_width=True)
    
# Load the image and make predictions
img = load_and_prep_image(image, scale=False) # don't scale images for EfficientNet predictions
pred_prob = model.predict(tf.expand_dims(img, axis=0)) # model accepts tensors of shape [None, 224, 224, 3]
pred_class = class_names[pred_prob.argmax()] # find the predicted class

st.write(f"## Predicted food: {pred_class}, with Probability: {pred_prob.max():.2f}")